Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3277 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9509. Min Range: -2.9509

Max Act: 2.9509. Min Act: -0.0000

Data Index: 1120441 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 2.9509. Min Range: -2.9509

Max Act: 2.2281. Min Act: -0.0000

Data Index: 1297953 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 2.9509. Min Range: -2.9509

Max Act: 2.1961. Min Act: -0.0000

Data Index: 596804 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 2.9509. Min Range: -2.9509

Max Act: 1.9503. Min Act: -0.0000

Data Index: 471530 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 2.9509. Min Range: -2.9509

Max Act: 2.0313. Min Act: -0.0000

Data Index: 568662 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 2.9509. Min Range: -2.9509

Max Act: 1.8187. Min Act: -0.0000

Data Index: 1297944 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 2.9509. Min Range: -2.9509

Max Act: 2.1154. Min Act: -0.0000

Data Index: 1134976 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 2.9509. Min Range: -2.9509

Max Act: 1.9587. Min Act: -0.0000

Data Index: 1106147 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 2.9509. Min Range: -2.9509

Max Act: 2.0550. Min Act: -0.0000

Data Index: 363872 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 2.9509. Min Range: -2.9509

Max Act: 2.1556. Min Act: -0.0001

Data Index: 470785 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 2.9509. Min Range: -2.9509

Max Act: 2.0184. Min Act: -0.0000

Data Index: 938464 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 2.9509. Min Range: -2.9509

Max Act: 1.8124. Min Act: -0.0000

Data Index: 223784 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 2.9509. Min Range: -2.9509

Max Act: 1.8191. Min Act: -0.0000

Data Index: 170384 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 2.9509. Min Range: -2.9509

Max Act: 1.9053. Min Act: -0.0000

Data Index: 197161 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 2.9509. Min Range: -2.9509

Max Act: 1.8879. Min Act: -0.0000

Data Index: 1281346 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 2.9509. Min Range: -2.9509

Max Act: 1.8824. Min Act: -0.0000

Data Index: 629011 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 2.9509. Min Range: -2.9509

Max Act: 1.6812. Min Act: -0.0000

Data Index: 558131 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 2.9509. Min Range: -2.9509

Max Act: 1.9447. Min Act: -0.0000

Data Index: 123398 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 2.9509. Min Range: -2.9509

Max Act: 1.8209. Min Act: -0.0000

Data Index: 1246357 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 2.9509. Min Range: -2.9509

Max Act: 1.6589. Min Act: -0.0000

Data Index: 627633 (C4 (Web Text))

Max Activating Token Index: 746